<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
perioli_vgm_v5.0
This model is a fine-tuned version of microsoft/layoutlmv3-base on the sroie dataset. It achieves the following results on the evaluation set:
- Loss: 0.0111
- Precision: 0.9355
- Recall: 0.9667
- F1: 0.9508
- Accuracy: 0.9984
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 2000
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 0.55 | 100 | 0.0929 | 0.5373 | 0.48 | 0.5070 | 0.9805 |
No log | 1.1 | 200 | 0.0480 | 0.7325 | 0.7667 | 0.7492 | 0.9897 |
No log | 1.65 | 300 | 0.0425 | 0.6536 | 0.78 | 0.7112 | 0.9910 |
No log | 2.2 | 400 | 0.0290 | 0.8543 | 0.86 | 0.8571 | 0.9953 |
0.0746 | 2.75 | 500 | 0.0210 | 0.8627 | 0.88 | 0.8713 | 0.9963 |
0.0746 | 3.3 | 600 | 0.0182 | 0.8792 | 0.8733 | 0.8763 | 0.9963 |
0.0746 | 3.85 | 700 | 0.0113 | 0.8926 | 0.8867 | 0.8896 | 0.9974 |
0.0746 | 4.4 | 800 | 0.0119 | 0.9231 | 0.96 | 0.9412 | 0.9982 |
0.0746 | 4.95 | 900 | 0.0101 | 0.9290 | 0.96 | 0.9443 | 0.9984 |
0.0114 | 5.49 | 1000 | 0.0110 | 0.9329 | 0.9267 | 0.9298 | 0.9976 |
0.0114 | 6.04 | 1100 | 0.0132 | 0.9172 | 0.96 | 0.9381 | 0.9984 |
0.0114 | 6.59 | 1200 | 0.0110 | 0.9338 | 0.94 | 0.9369 | 0.9979 |
0.0114 | 7.14 | 1300 | 0.0114 | 0.9542 | 0.9733 | 0.9637 | 0.9984 |
0.0114 | 7.69 | 1400 | 0.0134 | 0.9355 | 0.9667 | 0.9508 | 0.9982 |
0.0035 | 8.24 | 1500 | 0.0132 | 0.9295 | 0.9667 | 0.9477 | 0.9982 |
0.0035 | 8.79 | 1600 | 0.0112 | 0.9295 | 0.9667 | 0.9477 | 0.9982 |
0.0035 | 9.34 | 1700 | 0.0098 | 0.9295 | 0.9667 | 0.9477 | 0.9982 |
0.0035 | 9.89 | 1800 | 0.0094 | 0.9295 | 0.9667 | 0.9477 | 0.9987 |
0.0035 | 10.44 | 1900 | 0.0115 | 0.9355 | 0.9667 | 0.9508 | 0.9984 |
0.0018 | 10.99 | 2000 | 0.0111 | 0.9355 | 0.9667 | 0.9508 | 0.9984 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.0+cu118
- Datasets 2.2.2
- Tokenizers 0.13.3